Previously we'd end up with an unnecessary mov for the thirs immediate value.
total instructions in shared programs : 851881 -> 851864 (-0.00%)
total gprs used in shared programs : 110295 -> 110295 (0.00%)
total local used in shared programs : 1020 -> 1020 (0.00%)
local gpr inst bytes
helped 0 0 17 17
hurt 0 0 0 0
Suggested-by: Karol Herbst <[email protected]>
Signed-off-by: Tobias Klausmann <[email protected]>
---
src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp | 15 ++++++++++++---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index 9875738..8bb5cf9 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -1008,13 +1008,22 @@ ConstantFolding::opnd(Instruction *i, ImmediateValue
&imm0, int s)
break;
case OP_MAD:
if (imm0.isInteger(0)) {
+ ImmediateValue imm1;
i->setSrc(0, i->getSrc(2));
i->src(0).mod = i->src(2).mod;
i->setSrc(1, NULL);
i->setSrc(2, NULL);
- i->op = i->src(0).mod.getOp();
- if (i->op != OP_CVT)
- i->src(0).mod = 0;
+ if (i->src(0).getImmediate(imm1)) {
+ bld.setPosition(i, false);
+ newi = bld.mkMov(i->getDef(0), bld.mkImm(imm1.reg.data.u64),
+ i->dType);
+ delete_Instruction(prog, i);
+ }
+ else {
+ i->op = i->src(0).mod.getOp();
+ if (i->op != OP_CVT)
+ i->src(0).mod = 0;
+ }
} else
if (i->subOp != NV50_IR_SUBOP_MUL_HIGH &&
(imm0.isInteger(1) || imm0.isInteger(-1))) {
--
2.10.0
_______________________________________________
Nouveau mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/nouveau
